O
on-policy
marlbenchmark/on-policy
This is the official implementation of Multi-Agent PPO (MAPPO).
★2.1kstars
Python
MIT
Updated: Today
📋 Project at a Glance
Tap to expand
What's this?Agents project leveraging algorithms and hanabi, built with Python, open-source
Who made it?Maintained by marlbenchmark team, 2.1K⭐ on GitHub, #577 out of 2166 in Agents
Why does it exist?In the Agents space, algorithms workflows faced efficiency bottlenecks. on-policy was built by marlbenchmark to address these hanabi challenges.
What can it do?Key use cases: mappo, mpes, multi-agent
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/marlbenchmark/on-policy | 官网 https://sites.google.com/view/mappo
🔗 github.com/marlbenchmark/on-policy | 官网 https://sites.google.com/view/mappo
Topics
algorithmshanabimappompesmulti-agentpposmacstarcraftii